Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Compensated Box-Jenkins transfer function for short term load forecast

Conference · · Proceedings of the American Power Conference; (United States)
OSTI ID:7116900
; ;  [1]
  1. Oklahoma Univ., Norman, OK (United States). School of Electrical Engineering and Computer Science

In the past years, the Box-Jenkins ARIMA method and the Box-Jenkins transfer function method (BJTF) have been among the most commonly used methods for short term electrical load forecasting. But when there exists a sudden change in the temperature, both methods tend to exhibit larger errors in the forecast. This paper demonstrates that the load forecasting errors resulting from either the BJ ARIMA model or the BJTF model are not simply white noise, but rather well-patterned noise, and the patterns in the noise can be used to improve the forecasts. Thus a compensated Box-Jenkins transfer method (CBJTF) is proposed to improve the accuracy of the load prediction. Some case studies have been made which result in about a 14-33% reduction of the root mean square (RMS) errors of the forecasts, depending on the compensation time period as well as the compensation method used.

OSTI ID:
7116900
Report Number(s):
CONF-920432--
Journal Information:
Proceedings of the American Power Conference; (United States), Journal Name: Proceedings of the American Power Conference; (United States) Vol. 54:2; ISSN PAPWA; ISSN 0097-2126
Country of Publication:
United States
Language:
English